Memory synchronisation of delayed neural networks via variable sampling control
Shenghuang He,
Hamid Reza Karimi,
Yanzhou Li and
Yaoxin Wang
International Journal of Systems Science, 2024, vol. 55, issue 16, 3412-3424
Abstract:
This paper tackles the challenge of memory synchronisation of delayed neural networks by implementing a variable sampling control approach. On the one hand, in the light of constructing novel Lyapunov functionals, the conservativeness of the criteria obtained for delayed neural networks is significantly reduced. On the other hand, in light of memory sampling method, the transmission delay is introduced in sampling control scheme, and the information can be fully utilised. The constructed Lyapunov functionals have an advantage, i.e. it is not necessary to be positive on sampling intervals, and also to be continuous at the sampling instants. Finally, to demonstrate the effectiveness and advantages of the proposed methods, two experimental simulations are conducted for delayed neural networks. Two simulations provide empirical evidence supporting the validity of the techniques developed in this study, highlighting their potential for practical application in delayed neural network systems.
Date: 2024
References: Add references at CitEc
Citations:
Downloads: (external link)
http://hdl.handle.net/10.1080/00207721.2024.2370326 (text/html)
Access to full text is restricted to subscribers.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:taf:tsysxx:v:55:y:2024:i:16:p:3412-3424
Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/TSYS20
DOI: 10.1080/00207721.2024.2370326
Access Statistics for this article
International Journal of Systems Science is currently edited by Visakan Kadirkamanathan
More articles in International Journal of Systems Science from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().